Multi-Task Learning for Arousal and Sleep Stage Detection Using Fully Convolutional Networks

TL;DR

This paper introduces FullSleepNet, a multi-task convolutional neural network that simultaneously detects arousals and classifies sleep stages from single-channel EEG, achieving state-of-the-art results and improving efficiency over traditional methods.

Contribution

The paper presents a novel multi-task learning model that unifies arousal detection and sleep stage classification as segmentation tasks using fully convolutional networks.

Findings

Achieves an AUPRC of 0.70 for arousal detection on two datasets.

Obtains sleep stage classification accuracy of 0.88 and 0.83 on respective datasets.

Demonstrates improved practicality and efficiency over traditional polysomnography methods.

Abstract

Objective. Sleep is a critical physiological process that plays a vital role in maintaining physical and mental health. Accurate detection of arousals and sleep stages is essential for the diagnosis of sleep disorders, as frequent and excessive occurrences of arousals disrupt sleep stage patterns and lead to poor sleep quality, negatively impacting physical and mental health. Polysomnography is a traditional method for arousal and sleep stage detection that is time-consuming and prone to high variability among experts. Approach. In this paper, we propose a novel multi-task learning approach for arousal and sleep stage detection using fully convolutional neural networks. Our model, FullSleepNet, accepts a full-night single-channel EEG signal as input and produces segmentation masks for arousal and sleep stage labels. FullSleepNet comprises four modules: a convolutional module to extract local features, a recurrent module to capture long-range dependencies, an attention mechanism to focus on relevant parts of the input, and a segmentation module to output final predictions. Main results. By unifying the two interrelated tasks as segmentation problems and employing a multi-task learning approach, FullSleepNet achieves state-of-the-art performance for arousal detection with an area under the precision-recall curve of 0.70 on Sleep Heart Health Study and Multi-Ethnic Study of Atherosclerosis datasets. For sleep stage classification, FullSleepNet obtains comparable performance on both datasets, achieving an accuracy of 0.88 on the former and an accuracy of 0.83 on the latter. Significance. Our results demonstrate that FullSleepNet offers improved practicality, efficiency, and accuracy for the detection of arousal and classification of sleep stages using raw EEG signals as input.